Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 72452
    Prev
    Next
    INDEX
    Explanations

    from/link

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centre
    -0.08
    ('/')↵
    -0.08
     sesso
    -0.07
     euth
    -0.07
    �
    -0.07
    淨
    -0.07
    isu
    -0.07
    壹
    -0.07
    到时候
    -0.07
    mtx
    -0.06
    POSITIVE LOGITS
    )();↵
    0.07
    FormGroup
    0.07
     FR
    0.07
    吸入
    0.07
    <&
    0.07
    .or
    0.07
    _ALLOC
    0.07
    强有力
    0.07
     Empire
    0.07
    上涨
    0.07
    Activations Density 0.002%

    No Known Activations